	US 12,131,562 B2
	Multi-modal segmentation network for enhanced semantic labeling in mapping
Sergi Adipraja Widjaja, Singapore (SG); Dhananjai Sharma, Singapore (SG); and Venice Erin B. Liong, Singapore (SG)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Dec. 12, 2022, as Appl. No. 18/079,498.
Application 18/079,498 is a continuation of application No. 17/553,429, filed on Dec. 16, 2021, granted, now 11,527,085.
Prior Publication US 2023/0260298 A1, Aug. 17, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G01C 21/32 (2006.01); G01S 7/48 (2006.01); G01S 17/42 (2006.01); G01S 17/86 (2020.01); G01S 17/89 (2020.01); G01S 17/931 (2020.01); G06T 7/10 (2017.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01); G06V 20/70 (2022.01); H04N 23/80 (2023.01)

CPC G06V 20/70 (2022.01) [G01S 7/4802 (2013.01); G01S 17/42 (2013.01); G01S 17/86 (2020.01); G01S 17/89 (2013.01); G01S 17/931 (2020.01); G06T 7/10 (2017.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01); H04N 23/80 (2023.01); G06T 2207/20084 (2013.01)]

29 Claims

1. A vehicle comprising:

at least one processor communicatively coupled to a camera and a LiDAR sensor; and

at least one memory storing instructions thereon that, when executed by the at least one processor, result in operations comprising:

generating at least one rich point feature for a point based on image data, the at least one rich point feature including a vector corresponding to a prediction score, the prediction score generated based on an application of a pixel-wise segmentation label to an enhanced pixel, wherein the vector includes vector values comprising the prediction score for the pixel-wise segmentation label applied to the enhanced pixel, the prediction score indicating a likelihood that the pixel-wise segmentation label corresponds to the point;

predicting a point-level semantic label for the point; and

providing the point-level semantic label to a mapping engine to generate a map.